Stefano Fiorucci

### Notes for the reviewer In `handle_optional_params` function: - I first find the optional params. This implementation is tested in Python 3.7 and 3.10, even if the annotations management is...

@tstadel @ZanSara I too have encountered this error in the past. I see two main alternative ways to address this issue (in the document store implementation): * Skip the metadata...

As we can see here, https://github.com/deepset-ai/haystack/blob/baf5ef81f75518272e325c18964f21f4c08a082d/haystack/document_stores/sql.py#L93-L97 currently meta is stored in a table, where both `name` and `value` are strings. As @danielbichuetti suggests, storing the whole meta as a **JSON**...

Hey @sjrl, thanks! For the moment, this error is resolved: if the metadata contains types that are not acceptable by the SQLDocumentStore, the specific values are skipped and we raise...

@sjrl I think that **this issue can be closed** as the problem has actually been solved. In any case, the interesting reflections we have made will remain here. What @TuanaCelik...

I tried to investigate this problem, but it's not easy :smile:. 1. First, in the YAML example reported by @tstadel, `custom_query` is `null` but now, after #2789, this parameter has...

Hey @julian-risch! I suppose that you are talking about this method: https://github.com/deepset-ai/haystack/blob/96bb9b5905dcef61264f40ead6eea1ecaf2991b7/haystack/nodes/reader/base.py#L33-L63 - (If-else block was removed with #2842) - I'm not sure that the scaling is redundant: based on...

[Embedded Milvus](https://github.com/milvus-io/embd-milvus) has been released!

Do you want to extract tables from one specific page? Sorry, but I don't understand your question...

At the moment, Camelot doesn't provide this feature. You can find the desired text and the page using a PDF parsing library (for example, https://github.com/izderadicka/pdfparser). Then, extract tables from the...